Search Results for author:
Found 10 papers, 1 papers with code
Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learning
We introduce a simple formulation for such learning, where the RL problem is constructed with a special ``CallPlanner'' action that terminates the bridge policy and hands control of the agent back to the planner.
Compositional Generative Modeling: A Single Model is Not All You Need
Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research.
Video Language Planning
We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data.
Learning Interactive Real-World Simulators
Applications of a real-world simulator range from controllable content creation in games and movies, to training embodied agents purely in simulation that can be directly deployed in the real world.
Local Neural Descriptor Fields: Locally Conditioned Object Representations for Manipulation
A robot operating in a household environment will see a wide range of unique and unfamiliar objects.
Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning
The core of our algorithm is PIGINet, a novel Transformer-based learning method that takes in a task plan, the goal, and the initial state, and predicts the probability of finding motion trajectories associated with the task plan.
Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization
Estimating the per-state expected cumulative rewards is a critical aspect of reinforcement learning approaches, however the experience is obtained, but standard deep neural-network function-approximation methods are often inefficient in this setting.
Model-based Reinforcement Learning
reinforcement-learning
+1
Active Learning of Abstract Plan Feasibility
Long horizon sequential manipulation tasks are effectively addressed hierarchically: at a high level of abstraction the planner searches over abstract action sequences, and when a plan is found, lower level motion plans are generated.
Learning Object-Based State Estimators for Household Robots
The robot may be called upon later to retrieve objects and will need a long-term object-based memory in order to know how to find them.
Residual Policy Learning
In these tasks, reinforcement learning from scratch remains data-inefficient or intractable, but learning a residual on top of the initial controller can yield substantial improvements.
